3 papers
cs.IR2025
BiCA: Effective Biomedical Dense Retrieval with Citation-Aware Hard Negatives
Aarush Sinha, Pavan Kumar S, Roshan Balaji +1
Hard negatives are essential for training effective retrieval models. Hard-negative mining typically relies on ranking documents using cross-encoders or static embedding models bas…
cs.LG2025
Functional Groups are All you Need for Chemically Interpretable Molecular Property Prediction
Roshan Balaji, Joe Bobby, Nirav Pravinbhai Bhatt
Molecular property prediction using deep learning (DL) models has accelerated drug and materials discovery, but the resulting DL models often lack interpretability, hindering their…
cs.LG2025
NovoMolGen: Rethinking Molecular Language Model Pretraining
Kamran Chitsaz, Roshan Balaji, Quentin Fournier +2
Designing de-novo molecules with desired property profiles requires efficient exploration of the vast chemical space ranging from to possible synthesizable cand…